dayhoff-tools 1.2.5__py3-none-any.whl → 1.3.1__py3-none-any.whl

dayhoff_tools/embedders.py

@@ -683,7 +683,7 @@ class Embedder(Processor):
         sequence_ids, sequences, sequence_lengths = zip(*batch)
 
         # Prepare sequences for tokenization
-        tokenizer_input = self.prepare_tokenizer_input(sequences)
+        tokenizer_input = self.prepare_tokenizer_input(list(sequences))
 
         # Tokenize sequences
         encoded_input = self.tokenizer.batch_encode_plus(

dayhoff_tools/fasta.py

@@ -25,7 +25,7 @@ def _clean_noncanonical_fasta(
 ) -> Optional[dict[str, str]]:
     """
     Read in a FASTA file containing multiple sequences, replace non-canonical amino acids,
-    remove empty sequences, and either write the sequences to a new FASTA file or return them as a dictionary.
+    remove stop codons, remove empty sequences, and either write the sequences to a new FASTA file or return them as a dictionary.
 
     Args:
         input_path (str): Path to the input FASTA file.
@@ -48,7 +48,11 @@ def _clean_noncanonical_fasta(
         for line in fasta_file:
             if line.startswith(">"):
                 if seq_id and seq_lines:
-                    seq = "".join(seq_lines).translate(str.maketrans("OJUZB", "XLCED"))
+                    seq = (
+                        "".join(seq_lines)
+                        .translate(str.maketrans("OJUZB", "XLCED"))
+                        .replace("*", "")
+                    )
                     if seq.strip():  # Only process non-empty sequences
                         sequences[seq_id] = seq
                         if output_path:
@@ -61,7 +65,11 @@ def _clean_noncanonical_fasta(
 
         # Process the last sequence
         if seq_id and seq_lines:
-            seq = "".join(seq_lines).translate(str.maketrans("OJUZB", "XLCED"))
+            seq = (
+                "".join(seq_lines)
+                .translate(str.maketrans("OJUZB", "XLCED"))
+                .replace("*", "")
+            )
             if seq.strip():  # Only process non-empty sequences
                 sequences[seq_id] = seq
                 if output_path:
@@ -92,7 +100,7 @@ def clean_noncanonical_fasta(
 ):
     """
     Read in a FASTA file containing multiple sequences and write the sequences to a new FASTA file.
-    Replace non-canonical amino acids along the way.
+    Replace non-canonical amino acids and remove stop codons along the way.
 
     Args:
         input_path (str): Path to the input FASTA file.
@@ -112,7 +120,7 @@ def clean_noncanonical_fasta_to_dict(
 ) -> dict[str, str]:
     """
     Read in a FASTA file containing multiple sequences and return the sequences as a dictionary.
-    Replace non-canonical amino acids along the way.
+    Replace non-canonical amino acids and remove stop codons along the way.
 
     Args:
         input_path (str): Path to the input FASTA file.

{dayhoff_tools-1.2.5.dist-info → dayhoff_tools-1.3.1.dist-info}/METADATA

@@ -1,11 +1,13 @@
 Metadata-Version: 2.3
 Name: dayhoff-tools
-Version: 1.2.5
+Version: 1.3.1
 Summary: Common tools for all the repos at Dayhoff Labs
 Author: Daniel Martin-Alarcon
 Author-email: dma@dayhofflabs.com
-Requires-Python: >=3.12,<4.0
+Requires-Python: >=3.10,<4.0
 Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Provides-Extra: embedders
@@ -24,13 +26,13 @@ Requires-Dist: pandas (>=2.2.3) ; extra == "embedders"
 Requires-Dist: pandas (>=2.2.3) ; extra == "full"
 Requires-Dist: pyyaml (>=6.0)
 Requires-Dist: questionary (>=2.0.1)
-Requires-Dist: rdkit (>=2025.3.2) ; extra == "full"
+Requires-Dist: rdkit-pypi (>=2022.9.5) ; extra == "full"
 Requires-Dist: requests (>=2.31.0)
 Requires-Dist: sentencepiece (>=0.2.0) ; extra == "embedders"
 Requires-Dist: sentencepiece (>=0.2.0) ; extra == "full"
 Requires-Dist: sqlalchemy (>=2.0.40,<3.0.0) ; extra == "full"
 Requires-Dist: toml (>=0.10)
-Requires-Dist: torch (>=2.5.0) ; extra == "embedders"
+Requires-Dist: torch (>=2.4.0) ; extra == "embedders"
 Requires-Dist: tqdm (>=4.67.1) ; extra == "embedders"
 Requires-Dist: tqdm (>=4.67.1) ; extra == "full"
 Requires-Dist: transformers (==4.36.2) ; extra == "full"

{dayhoff_tools-1.2.5.dist-info → dayhoff_tools-1.3.1.dist-info}/RECORD

@@ -13,8 +13,8 @@ dayhoff_tools/deployment/deploy_utils.py,sha256=StFwbqnr2_FWiKVg3xnJF4kagTHzndqq
 dayhoff_tools/deployment/job_runner.py,sha256=hljvFpH2Bw96uYyUup5Ths72PZRL_X27KxlYzBMgguo,5086
 dayhoff_tools/deployment/processors.py,sha256=LM0CQbr4XCb3AtLbrcuDQm4tYPXsoNqgVJ4WQYDjzJc,12406
 dayhoff_tools/deployment/swarm.py,sha256=YJfvVOcAS8cYcIj2fiN4qwC2leh0I9w5A4px8ZWSF6g,22833
-dayhoff_tools/embedders.py,sha256=fRkyWjHo8OmbNUBY_FwrgfvyiLqpmrpI57UAb1Szn1Y,36609
-dayhoff_tools/fasta.py,sha256=_kA2Cpiy7JAGbBqLrjElkzbcUD_p-nO2d5Aj1LVmOvc,50509
+dayhoff_tools/embedders.py,sha256=1THnmio4FYkBswy_xkIiwT-ZOEMn6ZLbTAa-Uz0-kyE,36615
+dayhoff_tools/fasta.py,sha256=USdemH4c_dNhWXOTAhldvlDi8eLHogsy0YSrOnODB5I,50773
 dayhoff_tools/file_ops.py,sha256=JlGowvr-CUJFidV-4g_JmhUTN9bsYuaxtqKmnKomm-Q,8506
 dayhoff_tools/h5.py,sha256=j1nxxaiHsMidVX_XwB33P1Pz9d7K8ZKiDZwJWQUUQSY,21158
 dayhoff_tools/intake/gcp.py,sha256=uCeEskhbEwJIYpN6ne6siT1dbpTizCjjel-hRe0kReE,3030
@@ -26,7 +26,7 @@ dayhoff_tools/intake/uniprot.py,sha256=BZYJQF63OtPcBBnQ7_P9gulxzJtqyorgyuDiPeOJq
 dayhoff_tools/logs.py,sha256=DKdeP0k0kliRcilwvX0mUB2eipO5BdWUeHwh-VnsICs,838
 dayhoff_tools/sqlite.py,sha256=jV55ikF8VpTfeQqqlHSbY8OgfyfHj8zgHNpZjBLos_E,18672
 dayhoff_tools/warehouse.py,sha256=8YbnQ--usrEgDQGfvpV4MrMji55A0rq2hZaOgFGh6ag,15896
-dayhoff_tools-1.2.5.dist-info/METADATA,sha256=EReORxgYDfQ8QCuuC0Z0z-jg5NxbQr4WNFIbNPQ2T18,2735
-dayhoff_tools-1.2.5.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-dayhoff_tools-1.2.5.dist-info/entry_points.txt,sha256=iAf4jteNqW3cJm6CO6czLxjW3vxYKsyGLZ8WGmxamSc,49
-dayhoff_tools-1.2.5.dist-info/RECORD,,
+dayhoff_tools-1.3.1.dist-info/METADATA,sha256=AyP_2vo_5tVylBVzP-EMkI3tPPxJIV-VpBdQxRQFIZU,2842
+dayhoff_tools-1.3.1.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+dayhoff_tools-1.3.1.dist-info/entry_points.txt,sha256=iAf4jteNqW3cJm6CO6czLxjW3vxYKsyGLZ8WGmxamSc,49
+dayhoff_tools-1.3.1.dist-info/RECORD,,